© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165409
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ска
    0.63
    IERC
    0.61
    с
    0.59
     Ска
    0.58
    唱歌
    0.57
     పాట
    0.57
     노래
    0.55
    لب
    0.54
    био
    0.54
     لب
    0.53
    POSITIVE LOGITS
     over
    0.68
     behind
    0.64
     kota
    0.59
     pribadi
    0.59
     untuk
    0.58
     kaca
    0.58
     IPS
    0.57
    2
    0.56
     community
    0.55
     Wednesday
    0.55
    Activations Density 0.003%

    No Known Activations